Step 3.5 Flash needs about 133.3 GB of memory at Q4_K_M (a 118.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 24 quants, from 0.5 GB to 161.7 GB (Q6_K).
Step 3.5 Flash – a sparse Mixture of Experts LLM with 256K context
Step 3.5 Flash is a 197B‑parameter foundation model built on a sparse MoE architecture. It activates only 11B parameters per token, enabling efficient reasoning and agentic tasks. The model supports a 262144‑token context window and is released under Apache‑2.0.
Good at
- Deep reasoning and multi‑step logic
- Agentic task execution
- Long‑context handling up to 256K tokens
Limits
- Requires large VRAM for full‑precision quant
- No vision or multimodal support
- License is Apache‑2.0
Best for
- Complex coding assistants
- Long‑form document analysis
- Agentic workflow automation
Who it’s for. Developers and researchers needing a high‑capacity reasoning model that can run locally on consumer hardware. The model is suitable for building agents that perform multi‑step reasoning and coding tasks while keeping data on premises.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.5 GB | 1.0 GB | Fits | Get file → | |
| IQ1_S | 39.4 GB | 44.6 GB | Too big | Get file → | |
| IQ1_M | 43.9 GB | 49.7 GB | Too big | Get file → | |
| IQ2_XXS | 51.4 GB | 58.1 GB | Too big | Get file → | |
| IQ2_XS | 57.5 GB | 64.9 GB | Too big | Get file → | |
| IQ2_S | 58.0 GB | 65.4 GB | Too big | Get file → | |
| IQ2_M | 64.0 GB | 72.2 GB | Too big | Get file → | |
| Q2_K_S | 65.9 GB | 74.3 GB | Too big | Get file → | |
| Q2_K | 71.8 GB | 80.9 GB | Too big | Get file → | |
| IQ3_XXS | 75.8 GB | 85.3 GB | Too big | Get file → | |
| IQ3_XS | 80.1 GB | 90.2 GB | Too big | Get file → | |
| Q3_K_S | 85.0 GB | 95.7 GB | Too big | Get file → | |
| IQ3_S | 85.0 GB | 95.7 GB | Too big | Get file → | |
| IQ3_M | 85.7 GB | 96.5 GB | Too big | Get file → | |
| Q3_K_M | 93.8 GB | 105.6 GB | Too big | Get file → | |
| Q3_K_L | 102.0 GB | 114.8 GB | Too big | Get file → | |
| IQ4_XS | 105.0 GB | 118.1 GB | Too big | Get file → | |
| Q4_0 | 111.3 GB | 125.2 GB | Too big | Get file → | |
| Q4_K_S | 111.5 GB | 125.4 GB | Too big | Get file → | |
| Q4_K_M | 118.6 GB | 133.3 GB | Too big | Get file → | |
| Q4_1 | 123.4 GB | 138.7 GB | Too big | Get file → | |
| Q5_K_S | 135.6 GB | 152.4 GB | Too big | Get file → | |
| Q5_K_M | 139.5 GB | 156.7 GB | Too big | Get file → | |
| Q6_K | 161.7 GB | 181.6 GB | Too big | Get file → |
For 8 GB VRAM use the "unknown" quant (0.47 GB file, 1 GB memory at 8 k context). For 16 GB VRAM the smallest quant with memory under 16 GB is not listed; the next available is IQ1_S (39.41 GB file, 44.6 GB memory). For 32 GB VRAM IQ1_S or IQ1_M are viable. Larger VRAM allows higher‑quality quants such as Q4_0 (111.3 GB file, 125.2 GB memory).
What GPU do you need for Step 3.5 Flash?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.0 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.0 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.0 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.0 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.0 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.0 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.0 GB in use).
- 48 GB VRAM: the best quant that fits is IQ1_S (39.4 GB file, about 44.6 GB in use).
Which Step 3.5 Flash quant should you choose?
Q4_K_M is the usual starting point for Step 3.5 Flash: it balances file size and quality well. Here it is a 118.6 GB file.
If memory is tight, the smallest file is the first one in the table at 0.5 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Step 3.5 Flash
How much VRAM does Step 3.5 Flash need?
About 133.3 GB at Q4_K_M with an 8K context window. That is the 118.6 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Step 3.5 Flash on an 8 GB GPU?
Yes, with the smaller files: the 0.5 GB file needs about 1.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Step 3.5 Flash GGUF?
It depends on the quant: file is 0.5 GB, IQ1_S is 39.4 GB, IQ1_M is 43.9 GB, IQ2_XXS is 51.4 GB, IQ2_XS is 57.5 GB, IQ2_S is 58.0 GB and 18 more.
What context length does Step 3.5 Flash support?
The GGUF header lists a trained context length of 262,144 tokens (256K).
Where can I download Step 3.5 Flash GGUF?
The files are on Hugging Face in the mradermacher/Step-3.5-Flash-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Step 3.5 Flash use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Step 3.5 Flash on 8 GB VRAM?
Only the "unknown" quant fits 8 GB VRAM, using 1 GB memory at 8 k context. Higher‑quality quants require more VRAM.
Does Step 3.5 Flash support vision or multimodal inputs?
No, the model is purely text‑based and does not include vision capabilities.
What license is Step 3.5 Flash released under?
The model is released under the Apache‑2.0 license.